© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1101
    Prev
    Next
    INDEX
    Explanations

    glad you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hoea
    1.40
    戳
    1.29
    Luong
    1.24
    孖
    1.22
    ouncement
    1.19
    chequer
    1.16
     organisers
    1.13
    erns
    1.12
    ﹗
    1.11
    aanse
    1.11
    POSITIVE LOGITS
    我可以
    2.46
     I
    2.43
     我
    2.40
     אני
    2.34
     tôi
    2.32
    You
    2.26
    我现在
    2.26
    I
    2.26
    you
    2.24
    我
    2.22
    Activations Density 2.461%

    No Known Activations